检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Cai, Danwei Li, Ming The Department of Electrical and Computer Engineering Duke University DurhamNC27705 United States The Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Data Science Research Center Duke Kunshan University Kunshan China

This paper focuses on the application of Conformers in speaker verification. Conformers, initially designed for Automatic Speech Recognition (ASR), excel at modeling both local and global contexts within speech signals effectively. Previous research has established that ASR and speaker verification tasks can naturally complement each other. Building on this synergistic relationship, this study introduces three strategies for leveraging ASR-pretrained Conformers in speaker verification: (1) Transfer learning: We use a pretrained ASR Conformer encoder to initialize the speaker embedding network, thereby enhancing model generalization and mitigating the risk of overfitting. (2) Knowledge distillation: We distill the complex capabilities of an ASR Conformer into a speaker verification model. This not only allows for flexibility in the student mode's network architecture but also incorporates frame-level ASR distillation loss as an auxiliary task to reinforce speaker verification. (3) Parameter-efficient transfer learning with speaker adaptation: A lightweight speaker adaptation module is proposed to convert ASR-derived features into speaker-specific embeddings, without altering the core architecture of the original ASR Conformer. This strategy facilitates the concurrent execution of ASR and speaker verification tasks within a singular model. Experiments were conducted on VoxCeleb datasets. The results are compelling: models employing ASR pretraining and knowledge distillation significantly outperform standard Conformers. Specifically, the best model using the ASR pretraining method achieved a 0.43% equal error rate (EER) on the VoxCeleb1-O test trial, while the knowledge distillation approach yielded a 0.38% EER. Furthermore, by adding a mere 4.92 million parameters to a 130.94 million-parameter ASR Conformer encoder, the speaker adaptation approach achieved a 0.45% EER, enabling parallel speech recognition and speaker verification within a single ASR Conformer encoder.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Multi-residual 2D network integrating spatial correlation for whole heart segmentation

引用

computers in Biology and Medicine 2024年 172卷 108261-108261页

作者： Huang, Yan Yang, Jinzhu Sun, Qi Yuan, Yuliang Li, Honghe Hou, Yang Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Liaoning Shenyang China School of Computer Science and Engineering Northeastern University Liaoning Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Liaoning Shenyang China Department of Radiology Shengjing Hospital of China Medical University Liaoning Shenyang China

Whole heart segmentation (WHS) has significant clinical value for cardiac anatomy, modeling, and analysis of cardiac function. This study aims to address the WHS accuracy on cardiac CT images, as well as the fast inference speed and low graphics processing unit (GPU) memory consumption required by practical clinical applications. Thus, we propose a multi-residual two-dimensional (2D) network integrating spatial correlation for WHS. The network performs slice-by-slice segmentation on three-dimensional cardiac CT images in a 2D encoder–decoder manner. In the network, a convolutional long short-term memory skip connection module is designed to perform spatial correlation feature extraction on the feature maps at different resolutions extracted by the sub-modules of the pre-trained ResNet-based encoder. Moreover, a decoder based on the multi-residual module is designed to analyze the extracted features from the perspectives of multi-scale and channel attention, thereby accurately delineating the various substructures of the heart. The proposed method is verified on a dataset of the multi-modality WHS challenge, an in-house WHS dataset, and a dataset of the abdominal organ segmentation challenge. The dice, Jaccard, average symmetric surface distance, Hausdorff distance, inference time, and maximum GPU memory of the WHS are 0.914, 0.843, 1.066 mm, 15.778 mm, 9.535 s, and 1905 MB, respectively. The proposed network has high accuracy, fast inference speed, minimal GPU memory consumption, strong robustness, and good generalization. It can be deployed to clinical practical applications for WHS and can be effectively extended and applied to other multi-organ segmentation fields. The source code is publicly available at https://***/nancy1984yan/MultiResNet-SC. © 2024 Elsevier Ltd

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Fully integrated hybrid microwave photonic receiver

引用

Photonics Research 2022年第6期10卷 1472-1483页

作者： JIACHEN LI SIGANG YANG HONGWEI CHEN XINGJUN WANG MINGHUA CHEN WEIWEN ZOU Beijing National Research Center for Information Science and Technology(BNRist) Department of Electronic EngineeringTsinghua UniversityBeijing 100084China State Key Laboratory of Advanced Optical Communications System and Networks Department of ElectronicsSchool of Electronics Engineering and Computer SciencePeking UniversityBeijing 100871China State Key Laboratory of Advanced Optical Communication Systems and Networks Intelligent Microwave Lightwave Integration Innovation Center(imLic)Department of Electronic EngineeringShanghai Jiao Tong UniversityShanghai 200240China

Microwave photonic receivers are a promising candidate in breaking the bandwidth limitation of traditional radio-frequency(RF)*** further balance the performance superiority with the requirements regarding size,weight,and power consumption(SWa P),the implementation of integrated microwave photonic microsystems has been considered an upgrade ***,up to now,to the best of our knowledge,chip-scale fully integrated microwave photonic receivers have not been reported due to the limitation of material *** this paper,we report a fully integrated hybrid microwave photonic receiver(FIH-MWPR)obtained by comprising the indium phosphide(In P)laser chip and the monolithic silicon-on-insulator(SOI)photonic circuit into the same substrate based on the low-coupling-loss micro-optics *** from the integration of all optoelectronic components,the packaged FIH-MWPR exhibits a compact volume of 6 cmand low power consumption of 1.2 *** FIH-MWPR supports a wide operation bandwidth from 2 to 18 ***,its RF-link performance to down-convert the RF signals to the intermediate frequency is experimentally characterized by measuring the link gain,the noise figure,and the spurious-free dynamic range metrics across the whole operation frequency ***,we have utilized it as a de-chirp receiver to process the broadband linear frequencymodulated(LFM)radar echo signals at different frequency bands(S-,C-,X-,and Ku-bands)and successfully demonstrated its high-resolution-ranging *** the best of our knowledge,this is the first realization of a chip-scale broadband fully integrated microwave photonic receiver,which is expected to be an important step in demonstrating the feasibility of all-integrated microwave photonic microsystems oriented to miniaturized application scenarios.

关键词： method microwave bands

来源：评论

学校读者我要写书评

暂无评论

SAMOYE: ZERO-SHOT SINGING VOICE CONVERSION MODEL BASED ON FEATURE DISENTANGLEMENT AND ENHANCEMENT

arXiv

引用

arXiv 2024年

作者： Wang, Zihao Ma, Le Feng, Yongsheng Pan, Xin Jin, Yuhang Zhang, Kejun Department of Computer Science Zhejiang University Hangzhou China Department of AI Music and Music Information Technology Central Conservatory of Music Beijing China Institute of Remote Sensing and Applications Beijing University of Civil Engineering and Architecture Beijing China Department of Computer Science Zhejiang University Hangzhou310027 China Department of Computer Science Zhejiang Key Laboratory of Intelligent Systems and Equipment for Digital Creativity Innovation Center of Yangtze River Delta Zhejiang University Hangzhou China

Singing voice conversion (SVC) aims to convert a singer’s voice to another singer’s from a reference audio while keeping the original semantics. However, existing SVC methods can hardly perform zero-shot due to incomplete feature disentanglement or dependence on the speaker look-up table. We propose the first open-source high-quality zero-shot SVC model SaMoye that can convert singing to human and non-human timbre. SaMoye disentangles the singing voice’s features into content, timbre, and pitch features, where we combine multiple ASR models and compress the content features to reduce timbre leakages. Besides, we enhance the timbre features by unfreezing the speaker encoder and mixing the speaker embedding with top-3 similar speakers. We also establish an unparalleled large-scale dataset to guarantee zero-shot performance, which comprises more than 1,815 hours of pure singing voice and 6,367 speakers. We conduct objective and subjective experiments to find that SaMoye outperforms other models in zero-shot SVC tasks even under extreme conditions like converting singing to animals’ timbre. The weights, code, dataset, and documents of SaMoye are publicly available on https://***/CarlWangChina/*** Codes 68Txx(Primary)14F05, 91Fxx(Secondary) Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Forecasting COVID-19 Infections in Gulf Cooperation Council (GCC) Countries using Machine Learning

arXiv

引用

arXiv 2023年

作者： Ismail, Leila Materwala, Huned Hennebelle, Alain Intelligent Distributed Computing and Systems Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al Ain Abu Dhabi15551 United Arab Emirates Independent Data Scientist and Engineer Al Ain Abu Dhabi United Arab Emirates

COVID-19 has infected more than 68 million people worldwide since it was first detected about a year ago. Machine learning time series models have been implemented to forecast COVID-19 infections. In this paper, we develop time series models for the Gulf Cooperation Council (GCC) countries using the public COVID-19 dataset from Johns Hopkins. The dataset set includes the one-year cumulative COVID-19 cases between 22/01/2020 to 22/01/2021. We developed different models for the countries under study based on the spatial distribution of the infection data. Our experimental results show that the developed models can forecast COVID-19 infections with high *** Codes 68-04, 68T05, 68T07, 68T20 © 2023, CC BY-NC-ND.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

M-SENA: An Integrated Platform for Multimodal Sentiment Analysis

arXiv

引用

arXiv 2022年

作者： Mao, Huisheng Yuan, Ziqi Xu, Hua Yu, Wenmeng Liu, Yihe Gao, Kai State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University China China School of Information Science and Engineering Hebei University of Science and Technology China

M-SENA is an open-sourced platform for Multimodal Sentiment Analysis. It aims to facilitate advanced research by providing flexible toolkits, reliable benchmarks, and intuitive demonstrations. The platform features a fully modular video sentiment analysis framework consisting of data management, feature extraction, model training, and result analysis modules. In this paper, we first illustrate the overall architecture of the M-SENA platform and then introduce features of the core modules. Reliable baseline results of different modality features and MSA benchmarks are also reported. Moreover, we use model evaluation and analysis tools provided by M-SENA to present intermediate representation visualization, on-the-fly instance test, and generalization ability test results. The source code of the platform is publicly available at https://***/thuiar/M-SENA. © 2022, CC BY-NC-SA.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Neural-Network-Based Recursive State Estimation for Nonlinear Networked systems With Binary-Encoding Mechanisms

引用

IEEE Transactions on Neural Networks and Learning systems 2025年第6期36卷 10072-10083页

作者： Yuhan Zhang Zidong Wang Lei Zou Wei Qian Shuxin Du College of Electrical Engineering and Automation Shandong University of Science and Technology Qingdao China Department of Computer Science Brunel University of London Middlesex Uxbridge U.K. College of Information Science and Technology Donghua University Shanghai China Engineering Research Center of Digitalized Textile and Fashion Technology Ministry of Education Shanghai China School of Electrical Engineering and Automation Henan Polytechnic University Jiaozuo China Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems School of Engineering Huzhou University Huzhou China

This work addresses the problem of recursive state estimation for networked control systems with unknown nonlinearities and binary-encoding mechanisms (BEMs). To enhance transmission reliability and reduce network resource consumption, BEMs are used to convert measurement signals into binary bit strings (BBSs) of limited length, which are then transmitted to the estimator through noisy communication channels. During transmission, random bit errors may occur in the BBSs due to channel noise. For the considered nonlinear networked control systems affected by random bit errors, a neural-network (NN)-based recursive estimation strategy is proposed, where an NN with a time-varying tuning scalar is employed to approximate the unknown nonlinearity of the networked control systems. By using the proposed strategy, the upper bounds of the estimation error of the system state and the trace of the estimation error of the NN weight (NNW) are first derived. These bounds are then minimized by recursively designing both the estimator gain matrix and the tuning scalar of the NNW. Finally, the effectiveness of the proposed estimation strategy is demonstrated through a numerical example.

关键词： Artificial neural networks State estimation Encoding Noise Networked control systems Electronic mail Symmetric matrices Estimation error Tuning Recursive estimation

来源：评论

学校读者我要写书评

暂无评论

Robust Imagined Speech Production from Electrocorticography with Adaptive Frequency Enhancement

Robust Imagined Speech Production from Electrocorticography ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xu Xu Chong Fu Junxin Chen Gwanggil Jeon David Camacho School of Computer Science and Engineering Northeastern University Shenyang China School of Software Dalian University of Technology Dalian China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China Engineering Research Center of Security Technology of Complex Network System Ministry of Education Shenyang China College of Information Technology Incheon National University Incheon Korea Department of Computer Systems Engineering Universidad Politécnica de Madrid Madrid Spain

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Imagined speech production with electrocorticography (ECoG) plays a crucial role in brain-computer interface system. A challenging issue is the great variation underlying the frequency bands of the ECoG signals’ encode information, which makes current methods difficult to generate imagined speech with stable quality among different persons. To this end, we propose a robust model to generate high-quality imagined speech from ECoG. A frequency enhancement branch is first designed to adaptively modulate the frequency information, whose product is fed into the following multi-scale channel attention module for robust feature extraction and fusion. By incorporating both the mel-spectrum and audio as training constraints, a multi-constraint decoder branch is finally constructed for imagined speech production. The performance of our model is evaluated on a high-quality dateset, i.e, Single Word Production Dutch-iBIDS. It yields Pearson correlation scores that are all above 0.8, and the standard deviationsare are all below 0.2 in different volunteers. Experimental results demonstrate that our model is effective and robust for ECoG based imagined speech production, and has advantages over peer methods.

关键词： Training Adaptation models Frequency modulation Correlation Neuroscience Production Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Feature Aggregating Network with Inter-Frame Interaction for Efficient Video Super-Resolution

Feature Aggregating Network with Inter-Frame Interaction for...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Yawei Li Zhao Zhang Suiyi Zhao Jicong Fan Haijun Zhang Mingliang Xu School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Kunming China Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China Department of Computer Science Harbin Institute of Technology Shenzhen China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China

Video super-resolution (VSR) on mobile devices aims to restore high-resolution frames from their low-resolution counterparts, satisfying the requirements of performance, FLOPs and latency. On one hand, partial feature processing, as a classic and acknowledged strategy, is developed in current studies to reach an appropriate trade-off between FLOPs and accuracy. However, the splitting of partial feature processing strategy are usually performed in a blind manner, thereby reducing the computational efficiency and performance gains. On the other hand, current methods for mobile platforms primarily treat VSR as an extension of single-image super-resolution to reduce model calculation and inference latency. However, lacking inter-frame information interaction in current methods results in a suboptimal latency and accuracy trade-off. To this end, we propose a novel architecture, termed Feature Aggregating Network with Inter-frame Interaction (FANI), a lightweight yet considering frame-wise correlation VSR network, which could achieve real-time inference while maintaining superior performance. Our FANI accepts adjacent multi-frame low-resolution images as input and generally consists of several fully-connection-embedded modules, i.e., Multi-stage Partial Feature Distillation (MPFD) for capturing multi-level feature representations. Moreover, considering the importance of inter-frame alignment, we further employ a tiny Attention-based Frame Alignment (AFA) module to promote inter-frame information flow and aggregation efficiently. Extensive experiments on the well-known dataset and real-world mobile device demonstrate the superiority of our proposed FANI, which means that our FANI could be well adapted to mobile devices and produce visually pleasing results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

D2NT: A High-Performing Depth-to-Normal Translator

D2NT: A High-Performing Depth-to-Normal Translator

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Yi Feng Bohuan Xue Ming Liu Qijun Chen Rui Fan Robotics & Artificial Intelligence Laboratory (RAIL) the State Key Laboratory of Intelligent Autonomous Systems and Frontiers Science Center for Intelligent Autonomous Systems the College of Electronic & Information Engineering Tongji University Shanghai P. R. China Department of Computer Science & Engineering the Hong Kong University of Science and Technology (Guangzhou) Hong Kong SAR P. R. China Robotics & Autonomous Systems Thrust of the Systems Hub the Hong Kong University of Science and Technol-ogy (Guangzhou) Nansha Guangzhou P. R. China

Surface normal holds significant importance in visual environmental perception, serving as a source of rich geometric information. However, the state-of-the-art (SoTA) surface normal estimators (SNEs) generally suffer from an unsatisfactory trade-off between efficiency and accuracy. To resolve this dilemma, this paper first presents a superfast depth-to-normal translator (D2NT), which can directly translate depth images into surface normal maps without calculating 3D coordinates. We then propose a discontinuity-aware gradient (DAG) filter, which adaptively generates gradient convolution kernels to improve depth gradient estimation. Finally, we propose a surface normal refinement module that can easily be integrated into any depth-to-normal SNEs, substantially improving the surface normal estimation accuracy. Our proposed algorithm demonstrates the best accuracy among all other existing real-time SNEs and achieves the SoTA trade-off between efficiency and accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：